RegSeg (no ImageNet pretraining)

Reported on 4 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical2 results

Semantic SegmentationonCityscapes test
Frame (fps)· 2021-11-18
30
best: 188.6 (STDC2-50)
Rethinking Dilated Convolution for Real-time Semantic Segmentation arXiv:2111.09957
Semantic SegmentationonCityscapes test
Time (ms)· 2021-11-18
33
best: 4000 (DeepLab)
Rethinking Dilated Convolution for Real-time Semantic Segmentation arXiv:2111.09957

Audio2 results

10-shot image generationonCityscapes test
Frame (fps)· 2021-11-18
30
best: 188.6 (STDC2-50)
Rethinking Dilated Convolution for Real-time Semantic Segmentation arXiv:2111.09957
10-shot image generationonCityscapes test
Time (ms)· 2021-11-18
33
best: 4000 (DeepLab)
Rethinking Dilated Convolution for Real-time Semantic Segmentation arXiv:2111.09957